Due Jun 28, 2:59 AM EDT
Which of the following do you typically see in a ConvNet? (Check all that apply.)
True, fully-connected layers are often used after flattening a volume to output a set of classes in classification.
True, as seen in the case studies.
In order to be able to build very deep networks, we usually only use pooling layers to downsize the height/width of the activation volumes while convolutions are used with “valid” padding. Otherwise, we would downsize the input of the model too quickly.
Correct!
Training a deeper network (for example, adding additional layers to the network) allows the network to fit more complex functions and thus almost always results in lower training error. For this question, assume we’re referring to “plain” networks.
Correct, Resnets are here to help us train very deep neural networks.
The following equation captures the computation in a ResNet block. What goes into the two blanks above?
Correct
Which ones of the following statements on Residual Networks are true? (Check all that apply.)
This is true.
This is true.
Suppose you have an input volume of dimension nH x nW x nC. Which of the following statements you agree with? (Assume that “1x1 convolutional layer” below always uses a stride of 1 and no padding.)
This is correct.
Yes, a 1x1 convolutional layer with a small number of filters is going to reduce nC but will keep the dimensions nH and nW
Which ones of the following statements on Inception Networks are true? (Check all that apply.)
Which of the following are common reasons for using open-source implementations of ConvNets (both the model and/or weights)? Check all that apply.
True
True
In Depthwise Separable Convolution you:
Fill in the missing dimensions shown in the image below (marked W, Y, Z).
